CN112949305A - Negative feedback information acquisition method, device, equipment and storage medium - Google Patents
Negative feedback information acquisition method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN112949305A CN112949305A CN202110524058.6A CN202110524058A CN112949305A CN 112949305 A CN112949305 A CN 112949305A CN 202110524058 A CN202110524058 A CN 202110524058A CN 112949305 A CN112949305 A CN 112949305A
- Authority
- CN
- China
- Prior art keywords
- information
- question
- emotion
- preset
- target
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/166—Editing, e.g. inserting or deleting
- G06F40/186—Templates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/211—Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars
Abstract
The invention relates to artificial intelligence and provides a negative feedback information acquisition method, a device, equipment and a storage medium. The method includes the steps of determining an object to be acquired according to an information acquisition request, obtaining question and answer information corresponding to the object to be acquired, extracting target information from the question and answer information, calculating text similarity of the target information and preset information, analyzing the question and answer information to obtain emotion degree of the target information, obtaining an object weight of the object to be acquired according to the text similarity and the emotion degree, weighting and calculating the emotion degree and the text similarity according to the object weight to obtain satisfaction degree of a user in the object to be acquired, extracting user questions and model answers from the question and answer information when the satisfaction degree is smaller than a preset value, and determining the user questions and the model answers as response results of the acquisition request. The invention can quickly and accurately acquire a large amount of negative feedback information. In addition, the invention also relates to a block chain technology, and the response result can be stored in the block chain.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a negative feedback information acquisition method, a device, equipment and a storage medium.
Background
According to statistics, the current intelligent customer service robot cannot fully understand the intention of the user when solving the user problem. In order to improve the accuracy of the customer service robot in identifying the user intention, a large amount of real negative feedback information provided by the user needs to be collected to adjust the intention identification model. For this reason, a user negative feedback information acquisition scheme ensues.
In the existing user negative feedback information acquisition scheme, data information actively fed back by a user is collected to serve as negative feedback information, however, in most scenes, the user cannot actively feed back the identification condition, and a large amount of negative feedback information cannot be acquired quickly.
Disclosure of Invention
In view of the foregoing, there is a need for a negative feedback information collecting method, apparatus, device and storage medium, which can quickly and accurately acquire a large amount of negative feedback information.
On one hand, the invention provides a negative feedback information acquisition method, which comprises the following steps:
when an information acquisition request is received, determining an object to be acquired according to the information acquisition request, and acquiring question and answer information corresponding to the object to be acquired;
extracting target information from the question and answer information, and calculating text similarity of the target information and preset information;
analyzing the question-answer information to obtain the emotion degree of the target information;
acquiring an object weight of the object to be acquired according to the text similarity and the emotion degree, wherein the object weight is the weight occupied by the text similarity;
weighting and calculating the emotion degree and the text similarity according to the object weight to obtain the satisfaction degree of the user in the object to be collected, and detecting whether the satisfaction degree is smaller than a preset value;
when the satisfaction is smaller than the preset value, extracting user questions and model answers from the question-answering information;
and determining the user question and the model answer as a response result of the acquisition request.
According to a preferred embodiment of the present invention, the determining the object to be acquired according to the information acquisition request includes:
analyzing the message of the information acquisition request to obtain the data information carried by the message;
acquiring a preset label, wherein the preset label is used for indicating a question and answer field;
and acquiring information corresponding to the preset label from the data information as the object to be acquired.
According to a preferred embodiment of the present invention, the obtaining of the question and answer information corresponding to the object to be collected includes:
acquiring a log list;
acquiring a preset query template, and writing the object to be acquired into the preset query template to obtain a query statement;
running the query statement in the log list to obtain a target log;
and extracting information indicating a text from the target log as the question and answer information.
According to a preferred embodiment of the present invention, the extracting target information from the question-answering information includes:
acquiring template sentences from the question and answer information according to a preset question and answer library;
removing the template sentences from the question and answer information to obtain user input information;
acquiring the generation time of the template statement from the target log, and acquiring the input time of the user input information from the target log;
and determining the user input information with the input time larger than the generation time as the target information.
According to a preferred embodiment of the present invention, the extracting user questions and model answers from the question-answering information includes:
determining the user input information of which the input time is less than or equal to the generation time as the user question;
determining a target sequence of the user questions in the question and answer information;
and selecting sentences adjacent to the target sequence in the question-answering information from the template sentences as model answers.
According to a preferred embodiment of the present invention, the calculating the text similarity between the target information and the preset information includes:
performing word segmentation processing on the target information to obtain information word segmentation;
determining the word segmentation position of the information word in the target information;
acquiring word segmentation vectors of the information word segmentation, and splicing the word segmentation vectors according to the word segmentation positions to obtain target vectors corresponding to the target information;
acquiring a preset vector of the preset information;
and calculating the distance between the target vector and the preset vector based on a cosine distance formula to obtain the text similarity.
According to a preferred embodiment of the present invention, the analyzing the question-answering information to obtain the emotion degree of the target information includes:
extracting keywords contained in the question and answer information;
vectorizing the keywords to obtain a feature vector;
acquiring a preset emotion word and acquiring an emotion vector of the preset emotion word;
calculating the emotion similarity of the feature vector and the emotion vector, and determining the preset emotion word with the highest emotion similarity as a target emotion word;
and acquiring an emotion score corresponding to the target emotion word as the emotion degree.
In another aspect, the present invention further provides a negative feedback information collecting apparatus, including:
the device comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for determining an object to be acquired according to an information acquisition request when the information acquisition request is received, and acquiring question and answer information corresponding to the object to be acquired;
the computing unit is used for extracting target information from the question answering information and computing the text similarity between the target information and preset information;
the analysis unit is used for analyzing the question answering information to obtain the emotion degree of the target information;
the acquiring unit is further configured to acquire an object weight of the object to be acquired according to the text similarity and the emotion degree, where the object weight is a weight occupied by the text similarity;
the detection unit is used for weighting and calculating the emotion degree and the text similarity according to the object weight to obtain the satisfaction degree of the user in the object to be collected and detecting whether the satisfaction degree is smaller than a preset value;
the extracting unit is used for extracting user questions and model answers from the question and answer information when the satisfaction degree is smaller than the preset value;
and the determining unit is used for determining the user question and the model answer as a response result of the acquisition request.
In another aspect, the present invention further provides an electronic device, including:
a memory storing computer readable instructions; and
and the processor executes the computer readable instructions stored in the memory to realize the negative feedback information acquisition method.
In another aspect, the present invention further provides a computer-readable storage medium, in which computer-readable instructions are stored, and the computer-readable instructions are executed by a processor in an electronic device to implement the negative feedback information acquisition method.
According to the technical scheme, the object to be acquired can be accurately determined through the information acquisition request, so that the question and answer information can be accurately acquired, the satisfaction degree can be accurately determined from multiple dimensions through the similarity between the target information and the preset information and the emotion degree of the target information in the question and answer information, whether negative feedback information exists in the object to be acquired can be accurately determined according to the satisfaction degree, so that the negative feedback information can be accurately acquired, and in addition, the identification condition is not required to be actively fed back by a user, so that a large amount of negative feedback information can be quickly acquired on the premise of not being influenced by the user.
Drawings
FIG. 1 is a flow chart of a preferred embodiment of the negative feedback information acquisition method of the present invention.
Fig. 2 is a functional block diagram of a preferred embodiment of the negative feedback information collecting apparatus of the present invention.
FIG. 3 is a schematic structural diagram of an electronic device according to a preferred embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in detail with reference to the accompanying drawings and specific embodiments.
FIG. 1 is a flow chart of a preferred embodiment of the negative feedback information collection method of the present invention. The order of the steps in the flow chart may be changed and some steps may be omitted according to different needs.
The negative feedback information collecting method is applied to one or more electronic devices, which are devices capable of automatically performing numerical calculation and/or information processing according to preset or stored computer readable instructions, and the hardware thereof includes, but is not limited to, a microprocessor, an Application Specific Integrated Circuit (ASIC), a Programmable Gate Array (FPGA), a Digital Signal Processor (DSP), an embedded device, and the like.
The electronic device may be any electronic product capable of performing human-computer interaction with a user, for example, a Personal computer, a tablet computer, a smart phone, a Personal Digital Assistant (PDA), a game machine, an interactive Internet Protocol Television (IPTV), a smart wearable device, and the like.
The electronic device may include a network device and/or a user device. Wherein the network device includes, but is not limited to, a single network electronic device, an electronic device group consisting of a plurality of network electronic devices, or a Cloud Computing (Cloud Computing) based Cloud consisting of a large number of hosts or network electronic devices.
The network in which the electronic device is located includes, but is not limited to: the internet, a wide area Network, a metropolitan area Network, a local area Network, a Virtual Private Network (VPN), and the like.
S10, when an information acquisition request is received, determining an object to be acquired according to the information acquisition request, and acquiring question and answer information corresponding to the object to be acquired.
In at least one embodiment of the present invention, the information collection request is generated when the intelligent customer service robot detects that the user has information input or a preset button is triggered after replying to the user question. Wherein the preset button includes: a manual customer service button, an unsatisfied button, etc.
The information carried by the information acquisition request comprises: the object to be acquired, etc.
The object to be collected is used for indicating the question and answer field, and the object to be collected can be a number.
The question and answer information comprises information input by a user on the electronic equipment, and the question and answer information also comprises information generated by an intelligent customer service robot in the electronic equipment aiming at the object to be collected.
In at least one embodiment of the present invention, the electronic device determining, according to the information acquisition request, an object to be acquired includes:
analyzing the message of the information acquisition request to obtain the data information carried by the message;
acquiring a preset label, wherein the preset label is used for indicating a question and answer field;
and acquiring information corresponding to the preset label from the data information as the object to be acquired.
The information acquisition request may be a code, and the data information may be data in { }. The data information includes, but is not limited to: the object to be acquired.
Through the embodiment, the whole information acquisition request does not need to be analyzed, so that the data information acquisition efficiency can be improved, and the object to be acquired can be accurately determined through the mapping relation between the preset label and the question and answer field.
In at least one embodiment of the present invention, the acquiring, by the electronic device, question and answer information corresponding to the object to be acquired includes:
acquiring a log list;
acquiring a preset query template, and writing the object to be acquired into the preset query template to obtain a query statement;
running the query statement in the log list to obtain a target log;
and extracting information indicating a text from the target log as the question and answer information.
The log list stores multiple field logs of the question and answer fields, and the question and answer behavior information of the corresponding question and answer fields is recorded in each field log.
For example: in the session log a, the user a (time, 10: 20; text asking for how much the weather is today), the robot (time, 10: 22; text, answer is the cloudy day).
The query statement can be quickly generated through the preset query template and the object to be acquired, the target log can be accurately determined by operating the query statement in the log list, and therefore the question and answer information can be accurately acquired.
And S11, extracting target information from the question and answer information, and calculating the text similarity between the target information and preset information.
In at least one embodiment of the present invention, the target information refers to feedback information generated by a user for a reply sentence of the intelligent customer service robot.
The text similarity refers to the similarity between the target information and the preset information.
In at least one embodiment of the present invention, the electronic device extracting target information from the question and answer information includes:
acquiring template sentences from the question and answer information according to a preset question and answer library;
removing the template sentences from the question and answer information to obtain user input information;
acquiring the generation time of the template statement from the target log, and acquiring the input time of the user input information from the target log;
and determining the user input information with the input time larger than the generation time as the target information.
And a plurality of answer templates of the intelligent customer service robot are stored in the preset question-answering database.
The user input information includes, but is not limited to: question sentences of the user, evaluation sentences of the user aiming at the template sentences, behaviors of the user aiming at the template sentences and the like.
The generation time refers to the time when the intelligent customer service robot replies the question sentences of the user, and the input time refers to the time when the user sends the input information of the user.
The template statement can be accurately acquired from the question and answer information through the preset question and answer library, so that the user input information can be accurately acquired.
In at least one embodiment of the present invention, the calculating, by the electronic device, the text similarity between the target information and preset information includes:
performing word segmentation processing on the target information to obtain information word segmentation;
determining the word segmentation position of the information word in the target information;
acquiring word segmentation vectors of the information word segmentation, and splicing the word segmentation vectors according to the word segmentation positions to obtain target vectors corresponding to the target information;
acquiring a preset vector of the preset information;
and calculating the distance between the target vector and the preset vector based on a cosine distance formula to obtain the text similarity.
The word segmentation position refers to the position of the information word segmentation in the target information.
The preset information refers to preset information feedback or behavior feedback which is unsatisfactory to a user.
And splicing the word segmentation vectors through the word segmentation positions, so that a target vector containing the semantics in the target information can be accurately generated, and the text similarity can be accurately calculated.
Specifically, the electronic device performs word segmentation processing on the target information to obtain information word segmentation, including:
segmenting the target information based on a preset dictionary to obtain a plurality of segmentation paths and path segmentation words of each segmentation path;
acquiring a segmentation weight of the path segmentation from the preset dictionary;
calculating the segmentation probability of each segmentation path according to the word segmentation weight;
and determining the segmentation path with the highest segmentation probability as a target path, and determining the path word segmentation corresponding to the target path as the information word segmentation.
The preset dictionary stores a plurality of vocabularies and vocabulary weight values of each vocabulary.
The target information is segmented through the preset dictionary, the multiple segmentation paths can be comprehensively determined, the target paths can be accurately determined through the segmentation probability, and therefore the information word segmentation can be accurately determined.
And S12, analyzing the question and answer information to obtain the emotion degree of the target information.
In at least one embodiment of the present invention, the emotion degree is determined by analyzing emotion similarity between the keyword in the question and answer information and a preset emotion word, and by an emotion score corresponding to the preset emotion word with the highest emotion similarity.
In at least one embodiment of the present invention, the analyzing, by the electronic device, the question-answer information to obtain the emotion degree of the target information includes:
extracting keywords contained in the question and answer information;
vectorizing the keywords to obtain a feature vector;
acquiring a preset emotion word and acquiring an emotion vector of the preset emotion word;
calculating the emotion similarity of the feature vector and the emotion vector, and determining the preset emotion word with the highest emotion similarity as a target emotion word;
and acquiring an emotion score corresponding to the target emotion word as the emotion degree.
The keywords refer to words capable of representing the question and answer information.
The preset emotional words may include, but are not limited to: exciting.
By the implementation method, the characteristic vector representing the question-answering information can be accurately determined, and the target emotion word can be accurately determined from the preset emotion words by calculating the emotion similarity, so that the emotion degree can be accurately determined.
Specifically, the obtaining, by the electronic device, an emotion vector of the preset emotion word includes:
determining a generation vector table of the feature vector according to the keyword;
and acquiring a vector corresponding to the preset emotion word from the generated vector table as the emotion vector.
By acquiring the emotion vector from the vector generation table of the feature vector, the vector corresponding to the preset emotion word can be acquired from the same dimension as the keyword, and the determination accuracy of the emotion similarity is improved.
And S13, obtaining the object weight of the object to be collected according to the text similarity and the emotion degree.
In at least one embodiment of the present invention, the object weight refers to a weight occupied by the text similarity in a user satisfaction recognition process.
In at least one embodiment of the present invention, the obtaining, by the electronic device, the object weight of the object to be collected according to the text similarity and the emotion degree includes:
determining a similar interval of the text similarity in a configuration library, and determining an emotion interval of the emotion similarity in the configuration library;
and acquiring weights corresponding to the similar interval and the emotion interval at the same time from the configuration library as the object weight.
The configuration library stores a plurality of dimensional intervals in two dimensions and the weight corresponding to each dimensional interval. The two dimensions include a dimension in text similarity and a dimension in emotion. For example, the configuration library may store mapping relationships, specifically, as follows, a dimension interval [0.61, 0.80] in text similarity, a dimension interval [0.51, 0.75] in emotion similarity, and a weight of the corresponding text similarity is 0.4.
For example, the text similarity is 0.72, the emotion degree is 0.61, it is determined that the similarity interval is [0.61, 0.80], the emotion interval is [0.51, 0.75], and the object weight obtained from the configuration library and corresponding to both the similarity interval [0.61, 0.80] and the emotion interval [0.51, 0.75] is 0.4.
The similar interval and the emotion interval can be rapidly determined respectively through the text similarity and the emotion degree, and then the object weight can be accurately determined through the similar interval and the emotion interval.
Specifically, the obtaining, by the electronic device, weights corresponding to the similar interval and the emotion interval at the same time from the configuration library as the object weight includes:
acquiring a configuration template, wherein a first tag corresponding to the text similarity and a second tag corresponding to the emotion degree are stored in the configuration template;
writing the similar interval into a position corresponding to the first label, and writing the emotion interval into a position corresponding to the second label to obtain a weight query statement;
and querying the configuration library based on the weight query statement to obtain the object weight.
S14, weighting and calculating the emotion degree and the text similarity according to the object weight to obtain the satisfaction degree of the user in the object to be collected, and detecting whether the satisfaction degree is smaller than a preset value.
In at least one embodiment of the present invention, the satisfaction refers to a degree of satisfaction of the user with the object to be acquired.
The preset value is a value preset according to an application scene.
In at least one embodiment of the present invention, the electronic device performs weighting and calculation on the emotion degree and the text similarity according to the object weight, and obtaining the satisfaction of the user in the object to be collected includes:
calculating the product of the object weight and the text similarity to obtain a first numerical value;
calculating a difference value between the configuration value and the object weight value, and calculating a product of the difference value and the emotion degree to obtain a second numerical value;
and calculating the sum of the first value and the second value to obtain the satisfaction.
The configuration value refers to the sum of weights in the user satisfaction degree identification process, and is usually set to 1.
In at least one embodiment of the present invention, when the satisfaction is greater than or equal to the preset value, it indicates that the user is positive feedback to the object to be collected.
And S15, when the satisfaction is smaller than the preset value, extracting user questions and model answers from the question and answer information.
In at least one embodiment of the invention, the user question refers to a question posed by a user, and the model answer refers to a statement replied by the intelligent customer service robot for the user question.
In at least one embodiment of the present invention, the electronic device extracting the user question and the model answer from the question-answer information includes:
determining the user input information of which the input time is less than or equal to the generation time as the user question;
determining a target sequence of the user questions in the question and answer information;
and selecting sentences which are adjacent to the target sequence in the question-answering information from the template sentences as model answers.
The user question is provided before the intelligent customer service robot replies, so the input time and the generation time can accurately determine the user question, and further, the intelligent customer service robot can generate corresponding answers immediately after the user proposes the question, so the model answer can be accurately determined from the template sentence through the target sequence.
And S16, determining the user question and the model answer as a response result of the acquisition request.
It is emphasized that, in order to further ensure the privacy and security of the response result, the response result may also be stored in a node of a block chain.
In at least one embodiment of the present invention, after determining the user question and the model answer as a response result of the acquisition request, the method further comprises:
acquiring a request number of the information acquisition request;
generating prompt information according to the request number and the response result;
encrypting the prompt information by adopting a symmetric encryption technology to obtain a ciphertext;
and sending the ciphertext to the terminal equipment of the appointed contact person.
Through the embodiment, the prompt message can be sent to the designated contact person in time when the response result is generated, so that the collection efficiency of the response result is improved.
According to the technical scheme, the object to be acquired can be accurately determined through the information acquisition request, so that the question and answer information can be accurately acquired, the satisfaction degree can be accurately determined from multiple dimensions through the similarity between the target information and the preset information and the emotion degree of the target information in the question and answer information, whether negative feedback information exists in the object to be acquired can be accurately determined according to the satisfaction degree, so that the negative feedback information can be accurately acquired, and in addition, the identification condition is not required to be actively fed back by a user, so that a large amount of negative feedback information can be quickly acquired on the premise of not being influenced by the user.
Fig. 2 is a functional block diagram of a negative feedback information acquisition device according to a preferred embodiment of the present invention. The negative feedback information acquisition device 11 includes an acquisition unit 110, a calculation unit 111, an analysis unit 112, a detection unit 113, an extraction unit 114, a determination unit 115, a generation unit 116, an encryption unit 117, and a transmission unit 118. The module/unit referred to herein is a series of computer readable instruction segments that can be accessed by the processor 13 and perform a fixed function and that are stored in the memory 12. In the present embodiment, the functions of the modules/units will be described in detail in the following embodiments.
When receiving an information acquisition request, the acquisition unit 110 determines an object to be acquired according to the information acquisition request, and acquires question and answer information corresponding to the object to be acquired.
In at least one embodiment of the present invention, the information collection request is generated when the intelligent customer service robot detects that the user has information input or a preset button is triggered after replying to the user question. Wherein the preset button includes: a manual customer service button, an unsatisfied button, etc.
The information carried by the information acquisition request comprises: the object to be acquired, etc.
The object to be collected is used for indicating the question and answer field, and the object to be collected can be a number.
The question and answer information comprises information input by a user on electronic equipment, and the question and answer information also comprises information generated by an intelligent customer service robot in the electronic equipment aiming at the object to be collected.
In at least one embodiment of the present invention, the obtaining unit 110, according to the information acquisition request, determining the object to be acquired includes:
analyzing the message of the information acquisition request to obtain the data information carried by the message;
acquiring a preset label, wherein the preset label is used for indicating a question and answer field;
and acquiring information corresponding to the preset label from the data information as the object to be acquired.
The information acquisition request may be a code, and the data information may be data in { }. The data information includes, but is not limited to: the object to be acquired.
Through the embodiment, the whole information acquisition request does not need to be analyzed, so that the data information acquisition efficiency can be improved, and the object to be acquired can be accurately determined through the mapping relation between the preset label and the question and answer field.
In at least one embodiment of the present invention, the acquiring unit 110 acquires question and answer information corresponding to the object to be acquired, including:
acquiring a log list;
acquiring a preset query template, and writing the object to be acquired into the preset query template to obtain a query statement;
running the query statement in the log list to obtain a target log;
and extracting information indicating a text from the target log as the question and answer information.
The log list stores multiple field logs of the question and answer fields, and the question and answer behavior information of the corresponding question and answer fields is recorded in each field log.
For example: in the session log a, the user a (time, 10: 20; text asking for how much the weather is today), the robot (time, 10: 22; text, answer is the cloudy day).
The query statement can be quickly generated through the preset query template and the object to be acquired, the target log can be accurately determined by operating the query statement in the log list, and therefore the question and answer information can be accurately acquired.
The calculation unit 111 extracts target information from the question and answer information and calculates the text similarity between the target information and preset information.
In at least one embodiment of the present invention, the target information refers to feedback information generated by a user for a reply sentence of the intelligent customer service robot.
The text similarity refers to the similarity between the target information and the preset information.
In at least one embodiment of the present invention, the calculating unit 111 extracts target information from the question-answering information by:
acquiring template sentences from the question and answer information according to a preset question and answer library;
removing the template sentences from the question and answer information to obtain user input information;
acquiring the generation time of the template statement from the target log, and acquiring the input time of the user input information from the target log;
and determining the user input information with the input time larger than the generation time as the target information.
And a plurality of answer templates of the intelligent customer service robot are stored in the preset question-answering database.
The user input information includes, but is not limited to: question sentences of the user, evaluation sentences of the user aiming at the template sentences, behaviors of the user aiming at the template sentences and the like.
The generation time refers to the time when the intelligent customer service robot replies the question sentences of the user, and the input time refers to the time when the user sends the input information of the user.
The template statement can be accurately acquired from the question and answer information through the preset question and answer library, so that the user input information can be accurately acquired.
In at least one embodiment of the present invention, the calculating unit 111 calculates the text similarity between the target information and the preset information includes:
performing word segmentation processing on the target information to obtain information word segmentation;
determining the word segmentation position of the information word in the target information;
acquiring word segmentation vectors of the information word segmentation, and splicing the word segmentation vectors according to the word segmentation positions to obtain target vectors corresponding to the target information;
acquiring a preset vector of the preset information;
and calculating the distance between the target vector and the preset vector based on a cosine distance formula to obtain the text similarity.
The word segmentation position refers to the position of the information word segmentation in the target information.
The preset information refers to preset information feedback or behavior feedback which is unsatisfactory to a user.
And splicing the word segmentation vectors through the word segmentation positions, so that a target vector containing the semantics in the target information can be accurately generated, and the text similarity can be accurately calculated.
Specifically, the calculating unit 111 performs word segmentation processing on the target information, and obtaining information words comprises:
segmenting the target information based on a preset dictionary to obtain a plurality of segmentation paths and path segmentation words of each segmentation path;
acquiring a segmentation weight of the path segmentation from the preset dictionary;
calculating the segmentation probability of each segmentation path according to the word segmentation weight;
and determining the segmentation path with the highest segmentation probability as a target path, and determining the path word segmentation corresponding to the target path as the information word segmentation.
The preset dictionary stores a plurality of vocabularies and vocabulary weight values of each vocabulary.
The target information is segmented through the preset dictionary, the multiple segmentation paths can be comprehensively determined, the target paths can be accurately determined through the segmentation probability, and therefore the information word segmentation can be accurately determined.
The analysis unit 112 analyzes the question-answer information to obtain the emotion degree of the target information.
In at least one embodiment of the present invention, the emotion degree is determined by analyzing emotion similarity between the keyword in the question and answer information and a preset emotion word, and by an emotion score corresponding to the preset emotion word with the highest emotion similarity.
In at least one embodiment of the present invention, the analyzing unit 112 analyzes the question-answer information to obtain the emotion degree of the target information, including:
extracting keywords contained in the question and answer information;
vectorizing the keywords to obtain a feature vector;
acquiring a preset emotion word and acquiring an emotion vector of the preset emotion word;
calculating the emotion similarity of the feature vector and the emotion vector, and determining the preset emotion word with the highest emotion similarity as a target emotion word;
and acquiring an emotion score corresponding to the target emotion word as the emotion degree.
The keywords refer to words capable of representing the question and answer information.
The preset emotional words may include, but are not limited to: exciting.
By the implementation method, the characteristic vector representing the question-answering information can be accurately determined, and the target emotion word can be accurately determined from the preset emotion words by calculating the emotion similarity, so that the emotion degree can be accurately determined.
Specifically, the obtaining, by the analysis unit 112, an emotion vector of the preset emotion word includes:
determining a generation vector table of the feature vector according to the keyword;
and acquiring a vector corresponding to the preset emotion word from the generated vector table as the emotion vector.
By acquiring the emotion vector from the vector generation table of the feature vector, the vector corresponding to the preset emotion word can be acquired from the same dimension as the keyword, and the determination accuracy of the emotion similarity is improved.
The obtaining unit 110 obtains the object weight of the object to be collected according to the text similarity and the emotion degree.
In at least one embodiment of the present invention, the object weight refers to a weight occupied by the text similarity in a user satisfaction recognition process.
In at least one embodiment of the present invention, the obtaining unit 110 obtains the object weight of the object to be collected according to the text similarity and the emotion degree includes:
determining a similar interval of the text similarity in a configuration library, and determining an emotion interval of the emotion similarity in the configuration library;
and acquiring weights corresponding to the similar interval and the emotion interval at the same time from the configuration library as the object weight.
The configuration library stores a plurality of dimensional intervals in two dimensions and the weight corresponding to each dimensional interval. The two dimensions include a dimension in text similarity and a dimension in emotion. For example, the configuration library may store mapping relationships, specifically, as follows, a dimension interval [0.61, 0.80] in text similarity, a dimension interval [0.51, 0.75] in emotion similarity, and a weight of the corresponding text similarity is 0.4.
For example, the text similarity is 0.72, the emotion degree is 0.61, it is determined that the similarity interval is [0.61, 0.80], the emotion interval is [0.51, 0.75], and the object weight obtained from the configuration library and corresponding to both the similarity interval [0.61, 0.80] and the emotion interval [0.51, 0.75] is 0.4.
The similar interval and the emotion interval can be rapidly determined respectively through the text similarity and the emotion degree, and then the object weight can be accurately determined through the similar interval and the emotion interval.
Specifically, the obtaining unit 110 obtains, from the configuration library, weights corresponding to the similar interval and the emotion interval at the same time as the object weight, including:
acquiring a configuration template, wherein a first tag corresponding to the text similarity and a second tag corresponding to the emotion degree are stored in the configuration template;
writing the similar interval into a position corresponding to the first label, and writing the emotion interval into a position corresponding to the second label to obtain a weight query statement;
and querying the configuration library based on the weight query statement to obtain the object weight.
The detection unit 113 weights and calculates the emotion degree and the text similarity according to the object weight to obtain the satisfaction degree of the user in the object to be collected, and detects whether the satisfaction degree is smaller than a preset value.
In at least one embodiment of the present invention, the satisfaction refers to a degree of satisfaction of the user with the object to be acquired.
The preset value is a value preset according to an application scene.
In at least one embodiment of the present invention, the weighting and calculating, by the detection unit 113, the emotion degree and the text similarity according to the object weight, and obtaining the satisfaction of the user in the object to be collected includes:
calculating the product of the object weight and the text similarity to obtain a first numerical value;
calculating a difference value between the configuration value and the object weight value, and calculating a product of the difference value and the emotion degree to obtain a second numerical value;
and calculating the sum of the first value and the second value to obtain the satisfaction.
The configuration value refers to the sum of weights in the user satisfaction degree identification process, and is usually set to 1.
In at least one embodiment of the present invention, when the satisfaction is greater than or equal to the preset value, it indicates that the user is positive feedback to the object to be collected.
When the satisfaction is smaller than the preset value, the extracting unit 114 extracts the user question and the model answer from the question-answering information.
In at least one embodiment of the invention, the user question refers to a question posed by a user, and the model answer refers to a statement replied by the intelligent customer service robot for the user question.
In at least one embodiment of the present invention, the extracting unit 114 extracts the user question and the model answer from the question-answer information, including:
determining the user input information of which the input time is less than or equal to the generation time as the user question;
determining a target sequence of the user questions in the question and answer information;
and selecting sentences which are adjacent to the target sequence in the question-answering information from the template sentences as model answers.
The user question is provided before the intelligent customer service robot replies, so the input time and the generation time can accurately determine the user question, and further, the intelligent customer service robot can generate corresponding answers immediately after the user proposes the question, so the model answer can be accurately determined from the template sentence through the target sequence.
The determination unit 115 determines the user question and the model answer as a response result of the acquisition request.
It is emphasized that, in order to further ensure the privacy and security of the response result, the response result may also be stored in a node of a block chain.
In at least one embodiment of the present invention, after determining the user question and the model answer as the response result of the acquisition request, the obtaining unit 110 obtains the request number of the information acquisition request;
the generating unit 116 generates prompt information according to the request number and the response result;
the encryption unit 117 encrypts the prompt message by using a symmetric encryption technology to obtain a ciphertext;
the sending unit 118 sends the ciphertext to the terminal device of the designated contact.
Through the embodiment, the prompt message can be sent to the designated contact person in time when the response result is generated, so that the collection efficiency of the response result is improved.
According to the technical scheme, the object to be acquired can be accurately determined through the information acquisition request, so that the question and answer information can be accurately acquired, the satisfaction degree can be accurately determined from multiple dimensions through the similarity between the target information and the preset information and the emotion degree of the target information in the question and answer information, whether negative feedback information exists in the object to be acquired can be accurately determined according to the satisfaction degree, so that the negative feedback information can be accurately acquired, and in addition, the identification condition is not required to be actively fed back by a user, so that a large amount of negative feedback information can be quickly acquired on the premise of not being influenced by the user.
Fig. 3 is a schematic structural diagram of an electronic device according to a preferred embodiment of the method for acquiring negative feedback information according to the present invention.
In one embodiment of the present invention, the electronic device 1 includes, but is not limited to, a memory 12, a processor 13, and computer readable instructions stored in the memory 12 and executable on the processor 13, such as a negative feedback information acquisition program.
It will be appreciated by a person skilled in the art that the schematic diagram is only an example of the electronic device 1 and does not constitute a limitation of the electronic device 1, and that it may comprise more or less components than shown, or some components may be combined, or different components, e.g. the electronic device 1 may further comprise an input output device, a network access device, a bus, etc.
The Processor 13 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic device, discrete hardware component, etc. The processor 13 is an operation core and a control center of the electronic device 1, and is connected to each part of the whole electronic device 1 by various interfaces and lines, and executes an operating system of the electronic device 1 and various installed application programs, program codes, and the like.
Illustratively, the computer readable instructions may be partitioned into one or more modules/units that are stored in the memory 12 and executed by the processor 13 to implement the present invention. The one or more modules/units may be a series of computer readable instruction segments capable of performing specific functions, which are used for describing the execution process of the computer readable instructions in the electronic device 1. For example, the computer-readable instructions may be divided into an acquisition unit 110, a calculation unit 111, an analysis unit 112, a detection unit 113, an extraction unit 114, a determination unit 115, a generation unit 116, an encryption unit 117, and a transmission unit 118.
The memory 12 may be used for storing the computer readable instructions and/or modules, and the processor 13 implements various functions of the electronic device 1 by executing or executing the computer readable instructions and/or modules stored in the memory 12 and invoking data stored in the memory 12. The memory 12 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data created according to use of the electronic device, and the like. The memory 12 may include non-volatile and volatile memories, such as: a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), at least one magnetic disk storage device, a Flash memory device, or other storage device.
The memory 12 may be an external memory and/or an internal memory of the electronic device 1. Further, the memory 12 may be a memory having a physical form, such as a memory stick, a TF Card (Trans-flash Card), or the like.
The integrated modules/units of the electronic device 1 may be stored in a computer-readable storage medium if they are implemented in the form of software functional units and sold or used as separate products. Based on such understanding, all or part of the flow of the method according to the above embodiments may be implemented by hardware that is configured to be instructed by computer readable instructions, which may be stored in a computer readable storage medium, and when the computer readable instructions are executed by a processor, the steps of the method embodiments may be implemented.
Wherein the computer readable instructions comprise computer readable instruction code which may be in source code form, object code form, an executable file or some intermediate form, and the like. The computer-readable medium may include: any entity or device capable of carrying said computer readable instruction code, recording medium, U-disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM).
The block chain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.
With reference to fig. 1, the memory 12 in the electronic device 1 stores computer-readable instructions to implement a negative feedback information acquisition method, and the processor 13 can execute the computer-readable instructions to implement:
when an information acquisition request is received, determining an object to be acquired according to the information acquisition request, and acquiring question and answer information corresponding to the object to be acquired;
extracting target information from the question and answer information, and calculating text similarity of the target information and preset information;
analyzing the question-answer information to obtain the emotion degree of the target information;
acquiring an object weight of the object to be acquired according to the text similarity and the emotion degree;
weighting and calculating the emotion degree and the text similarity according to the object weight to obtain the satisfaction degree of the user in the object to be collected, and detecting whether the satisfaction degree is smaller than a preset value;
when the satisfaction is smaller than the preset value, extracting user questions and model answers from the question-answering information;
and determining the user question and the model answer as a response result of the acquisition request.
Specifically, the processor 13 may refer to the description of the relevant steps in the embodiment corresponding to fig. 1 for a specific implementation method of the computer readable instructions, which is not described herein again.
In the embodiments provided in the present invention, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is only one logical functional division, and other divisions may be realized in practice.
The computer readable storage medium has computer readable instructions stored thereon, wherein the computer readable instructions when executed by the processor 13 are configured to implement the steps of:
when an information acquisition request is received, determining an object to be acquired according to the information acquisition request, and acquiring question and answer information corresponding to the object to be acquired;
extracting target information from the question and answer information, and calculating text similarity of the target information and preset information;
analyzing the question-answer information to obtain the emotion degree of the target information;
acquiring an object weight of the object to be acquired according to the text similarity and the emotion degree;
weighting and calculating the emotion degree and the text similarity according to the object weight to obtain the satisfaction degree of the user in the object to be collected, and detecting whether the satisfaction degree is smaller than a preset value;
when the satisfaction is smaller than the preset value, extracting user questions and model answers from the question-answering information;
and determining the user question and the model answer as a response result of the acquisition request.
The modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.
In addition, functional modules in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional module.
The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference signs in the claims shall not be construed as limiting the claim concerned.
Furthermore, it is obvious that the word "comprising" does not exclude other elements or steps, and the singular does not exclude the plural. The plurality of units or devices may also be implemented by one unit or device through software or hardware. The terms first, second, etc. are used to denote names, but not any particular order.
Finally, it should be noted that the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.
Claims (10)
1. A negative feedback information acquisition method is characterized by comprising the following steps:
when an information acquisition request is received, determining an object to be acquired according to the information acquisition request, and acquiring question and answer information corresponding to the object to be acquired;
extracting target information from the question and answer information, and calculating text similarity of the target information and preset information;
analyzing the question-answer information to obtain the emotion degree of the target information;
acquiring an object weight of the object to be acquired according to the text similarity and the emotion degree, wherein the object weight is the weight occupied by the text similarity;
weighting and calculating the emotion degree and the text similarity according to the object weight to obtain the satisfaction degree of the user in the object to be collected, and detecting whether the satisfaction degree is smaller than a preset value;
when the satisfaction is smaller than the preset value, extracting user questions and model answers from the question-answering information;
and determining the user question and the model answer as a response result of the acquisition request.
2. The negative feedback information acquisition method of claim 1 wherein the determining an object to be acquired according to the information acquisition request comprises:
analyzing the message of the information acquisition request to obtain the data information carried by the message;
acquiring a preset label, wherein the preset label is used for indicating a question and answer field;
and acquiring information corresponding to the preset label from the data information as the object to be acquired.
3. The negative feedback information acquisition method of claim 1, wherein the acquiring of the question-answer information corresponding to the object to be acquired comprises:
acquiring a log list;
acquiring a preset query template, and writing the object to be acquired into the preset query template to obtain a query statement;
running the query statement in the log list to obtain a target log;
and extracting information indicating a text from the target log as the question and answer information.
4. The negative feedback information acquisition method as claimed in claim 3, wherein said extracting target information from the question answering information comprises:
acquiring template sentences from the question and answer information according to a preset question and answer library;
removing the template sentences from the question and answer information to obtain user input information;
acquiring the generation time of the template statement from the target log, and acquiring the input time of the user input information from the target log;
and determining the user input information with the input time larger than the generation time as the target information.
5. The negative feedback information collecting method of claim 4, wherein the extracting of the user's question and the model answer from the question and answer information comprises:
determining the user input information of which the input time is less than or equal to the generation time as the user question;
determining a target sequence of the user questions in the question and answer information;
and selecting sentences adjacent to the target sequence in the question-answering information from the template sentences as model answers.
6. The negative feedback information acquisition method of claim 1 wherein the calculating the text similarity of the target information to the preset information comprises:
performing word segmentation processing on the target information to obtain information word segmentation;
determining the word segmentation position of the information word in the target information;
acquiring word segmentation vectors of the information word segmentation, and splicing the word segmentation vectors according to the word segmentation positions to obtain target vectors corresponding to the target information;
acquiring a preset vector of the preset information;
and calculating the distance between the target vector and the preset vector based on a cosine distance formula to obtain the text similarity.
7. The negative feedback information collecting method of claim 1, wherein the analyzing the question and answer information to obtain the emotion degree of the target information comprises:
extracting keywords contained in the question and answer information;
vectorizing the keywords to obtain a feature vector;
acquiring a preset emotion word and acquiring an emotion vector of the preset emotion word;
calculating the emotion similarity of the feature vector and the emotion vector, and determining the preset emotion word with the highest emotion similarity as a target emotion word;
and acquiring an emotion score corresponding to the target emotion word as the emotion degree.
8. A negative feedback information acquisition apparatus, comprising:
the device comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for determining an object to be acquired according to an information acquisition request when the information acquisition request is received, and acquiring question and answer information corresponding to the object to be acquired;
the computing unit is used for extracting target information from the question answering information and computing the text similarity between the target information and preset information;
the analysis unit is used for analyzing the question answering information to obtain the emotion degree of the target information;
the acquiring unit is further configured to acquire an object weight of the object to be acquired according to the text similarity and the emotion degree, where the object weight is a weight occupied by the text similarity;
the detection unit is used for weighting and calculating the emotion degree and the text similarity according to the object weight to obtain the satisfaction degree of the user in the object to be collected and detecting whether the satisfaction degree is smaller than a preset value;
the extracting unit is used for extracting user questions and model answers from the question and answer information when the satisfaction degree is smaller than the preset value;
and the determining unit is used for determining the user question and the model answer as a response result of the acquisition request.
9. An electronic device, characterized in that the electronic device comprises:
a memory storing computer readable instructions; and
a processor executing computer readable instructions stored in the memory to implement the negative feedback information acquisition method of any of claims 1 to 7.
10. A computer-readable storage medium characterized by: the computer readable storage medium stores computer readable instructions, which are executed by a processor in an electronic device to implement the negative feedback information acquisition method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110524058.6A CN112949305B (en) | 2021-05-13 | 2021-05-13 | Negative feedback information acquisition method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110524058.6A CN112949305B (en) | 2021-05-13 | 2021-05-13 | Negative feedback information acquisition method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112949305A true CN112949305A (en) | 2021-06-11 |
| CN112949305B CN112949305B (en) | 2021-08-13 |
Family
ID=76233853
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110524058.6A Active CN112949305B (en) | 2021-05-13 | 2021-05-13 | Negative feedback information acquisition method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112949305B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113434321A (en) * | 2021-06-24 | 2021-09-24 | 平安国际智慧城市科技股份有限公司 | Method, device and equipment for processing deployment errors in operation and maintenance and storage medium |
Citations (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102799589A (en) * | 2011-05-25 | 2012-11-28 | 阿里巴巴集团控股有限公司 | Information pushing method and device |
| CN103970864A (en) * | 2014-05-08 | 2014-08-06 | 清华大学 | Emotion classification and emotion component analyzing method and system based on microblog texts |
| CN105512166A (en) * | 2015-10-30 | 2016-04-20 | 青岛智能产业技术研究院 | Traffic parallel method with mapping between microblog public sentiments and city road conditions |
| CN105743991A (en) * | 2016-03-31 | 2016-07-06 | 四川东鼎里智信息技术有限责任公司 | Information storage processing method of wearable device |
| CN105930416A (en) * | 2016-04-19 | 2016-09-07 | 中山大学 | Visualization processing method and system of user feedback information |
| CN107493352A (en) * | 2017-10-09 | 2017-12-19 | 陈包容 | A kind of mthods, systems and devices of tangible machine people intelligent training |
| US20180039621A1 (en) * | 2016-08-05 | 2018-02-08 | Monotype Imaging Inc. | Context analysis for message enhancement |
| WO2018027360A1 (en) * | 2016-08-06 | 2018-02-15 | 胡明祥 | Adjusting method during moments information-based advertisement pushing and pushing system |
| US20180060302A1 (en) * | 2016-08-24 | 2018-03-01 | Microsoft Technology Licensing, Llc | Characteristic-pattern analysis of text |
| CN107885718A (en) * | 2016-09-30 | 2018-04-06 | 腾讯科技（深圳）有限公司 | Semanteme determines method and device |
| CN108563779A (en) * | 2018-04-25 | 2018-09-21 | 北京计算机技术及应用研究所 | It is a kind of based on neural network without template natural language text answer generation method |
| CN108846050A (en) * | 2018-05-30 | 2018-11-20 | 重庆望江工业有限公司 | Core process knowledge intelligent method for pushing and system based on multi-model fusion |
| US20190095868A1 (en) * | 2017-09-28 | 2019-03-28 | Facebook, Inc. | Methods and systems for converting unstructured text into structured job postings |
| US20190155910A1 (en) * | 2017-11-17 | 2019-05-23 | Adobe Inc. | Highlighting Key Portions of Text Within a Document |
| CN110110061A (en) * | 2019-04-26 | 2019-08-09 | 同济大学 | Low-resource languages entity abstracting method based on bilingual term vector |
| CN110688452A (en) * | 2019-08-23 | 2020-01-14 | 重庆兆光科技股份有限公司 | Text semantic similarity evaluation method, system, medium and device |
| CN111652001A (en) * | 2020-06-04 | 2020-09-11 | 联想(北京)有限公司 | Data processing method and device |
| CN111813911A (en) * | 2020-06-30 | 2020-10-23 | 神思电子技术股份有限公司 | Knowledge automatic acquisition and updating system based on user supervision feedback and working method thereof |
| CN112650840A (en) * | 2020-12-04 | 2021-04-13 | 天津泰凡科技有限公司 | Intelligent medical question-answering processing method and system based on knowledge graph reasoning |
| CN112765306A (en) * | 2020-12-30 | 2021-05-07 | 金蝶软件（中国）有限公司 | Intelligent question answering method and device, computer equipment and storage medium |
-
2021
- 2021-05-13 CN CN202110524058.6A patent/CN112949305B/en active Active
Patent Citations (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102799589A (en) * | 2011-05-25 | 2012-11-28 | 阿里巴巴集团控股有限公司 | Information pushing method and device |
| CN103970864A (en) * | 2014-05-08 | 2014-08-06 | 清华大学 | Emotion classification and emotion component analyzing method and system based on microblog texts |
| CN105512166A (en) * | 2015-10-30 | 2016-04-20 | 青岛智能产业技术研究院 | Traffic parallel method with mapping between microblog public sentiments and city road conditions |
| CN105743991A (en) * | 2016-03-31 | 2016-07-06 | 四川东鼎里智信息技术有限责任公司 | Information storage processing method of wearable device |
| CN105930416A (en) * | 2016-04-19 | 2016-09-07 | 中山大学 | Visualization processing method and system of user feedback information |
| US20180039621A1 (en) * | 2016-08-05 | 2018-02-08 | Monotype Imaging Inc. | Context analysis for message enhancement |
| WO2018027360A1 (en) * | 2016-08-06 | 2018-02-15 | 胡明祥 | Adjusting method during moments information-based advertisement pushing and pushing system |
| US20180060302A1 (en) * | 2016-08-24 | 2018-03-01 | Microsoft Technology Licensing, Llc | Characteristic-pattern analysis of text |
| CN107885718A (en) * | 2016-09-30 | 2018-04-06 | 腾讯科技（深圳）有限公司 | Semanteme determines method and device |
| US20190095868A1 (en) * | 2017-09-28 | 2019-03-28 | Facebook, Inc. | Methods and systems for converting unstructured text into structured job postings |
| CN107493352A (en) * | 2017-10-09 | 2017-12-19 | 陈包容 | A kind of mthods, systems and devices of tangible machine people intelligent training |
| US20190155910A1 (en) * | 2017-11-17 | 2019-05-23 | Adobe Inc. | Highlighting Key Portions of Text Within a Document |
| CN108563779A (en) * | 2018-04-25 | 2018-09-21 | 北京计算机技术及应用研究所 | It is a kind of based on neural network without template natural language text answer generation method |
| CN108846050A (en) * | 2018-05-30 | 2018-11-20 | 重庆望江工业有限公司 | Core process knowledge intelligent method for pushing and system based on multi-model fusion |
| CN110110061A (en) * | 2019-04-26 | 2019-08-09 | 同济大学 | Low-resource languages entity abstracting method based on bilingual term vector |
| CN110688452A (en) * | 2019-08-23 | 2020-01-14 | 重庆兆光科技股份有限公司 | Text semantic similarity evaluation method, system, medium and device |
| CN111652001A (en) * | 2020-06-04 | 2020-09-11 | 联想(北京)有限公司 | Data processing method and device |
| CN111813911A (en) * | 2020-06-30 | 2020-10-23 | 神思电子技术股份有限公司 | Knowledge automatic acquisition and updating system based on user supervision feedback and working method thereof |
| CN112650840A (en) * | 2020-12-04 | 2021-04-13 | 天津泰凡科技有限公司 | Intelligent medical question-answering processing method and system based on knowledge graph reasoning |
| CN112765306A (en) * | 2020-12-30 | 2021-05-07 | 金蝶软件（中国）有限公司 | Intelligent question answering method and device, computer equipment and storage medium |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113434321A (en) * | 2021-06-24 | 2021-09-24 | 平安国际智慧城市科技股份有限公司 | Method, device and equipment for processing deployment errors in operation and maintenance and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112949305B (en) | 2021-08-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113032528B (en) | Case analysis method, case analysis device, case analysis equipment and storage medium | |
| CN112989826B (en) | Test question score determining method, device, equipment and medium based on artificial intelligence | |
| CN112417096A (en) | Question-answer pair matching method and device, electronic equipment and storage medium | |
| CN112686036B (en) | Risk text recognition method and device, computer equipment and storage medium | |
| CN113656547B (en) | Text matching method, device, equipment and storage medium | |
| CN113435196B (en) | Intention recognition method, device, equipment and storage medium | |
| CN113283675B (en) | Index data analysis method, device, equipment and storage medium | |
| CN111552800A (en) | Abstract generation method and device, electronic equipment and medium | |
| CN115222443A (en) | Client group division method, device, equipment and storage medium | |
| CN113094478B (en) | Expression reply method, device, equipment and storage medium | |
| CN113705468A (en) | Digital image identification method based on artificial intelligence and related equipment | |
| CN112949305B (en) | Negative feedback information acquisition method, device, equipment and storage medium | |
| CN114037545A (en) | Client recommendation method, device, equipment and storage medium | |
| CN113268597A (en) | Text classification method, device, equipment and storage medium | |
| CN113627186B (en) | Entity relation detection method based on artificial intelligence and related equipment | |
| CN113420545B (en) | Abstract generation method, device, equipment and storage medium | |
| CN113408278B (en) | Intention recognition method, device, equipment and storage medium | |
| CN113283677B (en) | Index data processing method, device, equipment and storage medium | |
| CN113343700B (en) | Data processing method, device, equipment and storage medium | |
| CN113535925B (en) | Voice broadcasting method, device, equipment and storage medium | |
| CN113342977B (en) | Invoice image classification method, device, equipment and storage medium | |
| CN113516205A (en) | Data classification method, device, equipment and storage medium based on artificial intelligence | |
| CN113486680A (en) | Text translation method, device, equipment and storage medium | |
| CN113269179A (en) | Data processing method, device, equipment and storage medium | |
| CN112199494A (en) | Medical information searching method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| REG | Reference to a national code |
Ref country code: HK Ref legal event code: DE Ref document number: 40053568 Country of ref document: HK |